School of Food and Environment, Dalian Univeristy of Technology, 2# Dagong Road, Liaodongwan New District, Panjin City, Liaoning Province, 124221, China.
School of Food and Environment, Dalian Univeristy of Technology, 2# Dagong Road, Liaodongwan New District, Panjin City, Liaoning Province, 124221, China.
Environ Pollut. 2018 Jul;238:121-129. doi: 10.1016/j.envpol.2018.03.026. Epub 2018 Mar 20.
Hyperspectral imaging technology has been investigated as a possible way to detect microplastics contamination in soil directly and efficiently in this study. Hyperspectral images with wavelength range between 400 and 1000 nm were obtained from soil samples containing different materials including microplastics, fresh leaves, wilted leaves, rocks and dry branches. Supervised classification algorithms such as support vector machine (SVM), mahalanobis distance (MD) and maximum likelihood (ML) algorithms were used to identify microplastics from the other materials in hyperspectral images. To investigate the effect of particle size and color, white polyethylene (PE) and black PE particles extracted from soil with two different particle size ranges (1-5 mm and 0.5-1 mm) were studied in this work. The results showed that SVM was the most applicable method for detecting white PE in soil, with the precision of 84% and 77% for PE particles in size ranges of 1-5 mm and 0.5-1 mm respectively. The precision of black PE detection achieved by SVM were 58% and 76% for particles of 1-5 mm and 0.5-1 mm respectively. Six kinds of household polymers including drink bottle, bottle cap, rubber, packing bag, clothes hanger and plastic clip were used to validate the developed method, and the classification precision of polymers were obtained from 79% to 100% and 86%-99% for microplastics particle 1-5 mm and 0.5-1 mm respectively. The results indicate that hyperspectral imaging technology is a potential technique to determine and visualize the microplastics with particle size from 0.5 to 5 mm on soil surface directly.
本研究探讨了利用高光谱成像技术直接、有效地检测土壤中微塑料污染的可能性。从含有微塑料、新鲜叶片、枯萎叶片、岩石和干树枝等不同材料的土壤样本中获取了波长范围在 400 至 1000nm 之间的高光谱图像。使用监督分类算法，如支持向量机 (SVM)、马氏距离 (MD) 和最大似然 (ML) 算法，从高光谱图像中的其他材料中识别微塑料。为了研究粒径和颜色的影响，从土壤中提取了两种不同粒径范围 (1-5mm 和 0.5-1mm) 的白色聚乙烯 (PE) 和黑色 PE 颗粒，并对其进行了研究。结果表明，SVM 是检测土壤中白色 PE 最适用的方法，对于粒径范围为 1-5mm 和 0.5-1mm 的 PE 颗粒，其精度分别为 84%和 77%。SVM 检测黑色 PE 的精度分别为 58%和 76%，用于粒径范围为 1-5mm 和 0.5-1mm 的颗粒。使用六种家用聚合物，包括饮料瓶、瓶盖、橡胶、塑料袋、衣架和塑料夹，对开发的方法进行了验证，聚合物的分类精度分别为 79%-100%和 86%-99%，用于粒径范围为 1-5mm 和 0.5-1mm 的微塑料颗粒。结果表明，高光谱成像技术是一种直接测定和可视化土壤表面粒径为 0.5 至 5mm 之间的微塑料的潜在技术。
